Calculating accuracy for a multi-label classification problem

[AjayTalati]

Hi @bartolsthoorn,

there seem to be few possible ways to try to do this,

Equivalent of TensorFlow's Sigmoid Cross Entropy With Logits in Pytorch

@AjayTalati I managed to use BCELoss, binary_crossentropy and MultiLabelSoftMarginLoss on a MultiLabel problem Here is the basic code def train(epoch): model.train() for batch_idx, (data, target) in enumerate(train_loader): # data, target = data.cuda(async=True), target.cuda(async=True) # On GPU data, target = Variable(data), Variable(target) optimizer.zero_grad() output = model(data) loss = F.binary_cross_entropy(output, target) loss.bac…

We really need a working example, so if you do get it working, perhaps you could post a gist?

Kind regards,

Ajay